CVE-2025-59425
Full vulnerability record from the local CVENow database.
Description
vLLM is an inference and serving engine for large language models (LLMs). Before version 0.11.0rc2, the API key support in vLLM performs validation using a method that was vulnerable to a timing attack. API key validation uses a string comparison that takes longer the more characters the provided API key gets correct. Data analysis across many attempts could allow an attacker to determine when it finds the next correct character in the key sequence. Deployments relying on vLLM's built-in API key validation are vulnerable to authentication bypass using this technique. Version 0.11.0rc2 fixes the issue.
Severity
HIGH
CVSS score
7.5
(v3.1)
Vulnerability status
Analyzed
Source identifier
Published
2025-10-07 14:15:38.950000
Last modified
2026-10-19 16:10:00.260000
View original CVE JSON
{
"id": "CVE-2025-59425",
"sourceIdentifier": "[email protected]",
"published": "2025-10-07T14:15:38.950",
"lastModified": "2026-10-19T16:10:00.260",
"vulnStatus": "Analyzed",
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "vLLM is an inference and serving engine for large language models (LLMs). Before version 0.11.0rc2, the API key support in vLLM performs validation using a method that was vulnerable to a timing attack. API key validation uses a string comparison that takes longer the more characters the provided API key gets correct. Data analysis across many attempts could allow an attacker to determine when it finds the next correct character in the key sequence. Deployments relying on vLLM's built-in API key validation are vulnerable to authentication bypass using this technique. Version 0.11.0rc2 fixes the issue."
},
{
"lang": "es",
"value": "vLLM es un motor de inferencia y servicio para modelos de lenguaje grandes (LLM). Antes de la versión 0.11.0rc2, el soporte de clave API en vLLM realiza la validación utilizando un método que era vulnerable a un ataque de temporización. La validación de clave API utiliza una comparación de cadenas que tarda más cuanto más caracteres correctos obtiene la clave API proporcionada. El análisis de datos a través de muchos intentos podría permitir a un atacante determinar cuándo encuentra el siguiente carácter correcto en la secuencia de la clave. Las implementaciones que dependen de la validación de clave API integrada de vLLM son vulnerables a la omisión de autenticación utilizando esta técnica. La versión 0.11.0rc2 corrige el problema."
}
],
"affected": [
{
"source": "[email protected]",
"affectedData": [
{
"vendor": "vllm-project",
"product": "vllm",
"versions": [
{
"version": "< 0.11.0rc2",
"status": "affected"
}
]
}
]
}
],
"metrics": {
"cvssMetricV31": [
{
"source": "[email protected]",
"type": "Secondary",
"cvssData": {
"version": "3.1",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N",
"baseScore": 7.5,
"baseSeverity": "HIGH",
"attackVector": "NETWORK",
"attackComplexity": "LOW",
"privilegesRequired": "NONE",
"userInteraction": "NONE",
"scope": "UNCHANGED",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"availabilityImpact": "NONE"
},
"exploitabilityScore": 3.9,
"impactScore": 3.6
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"timestamp": "2025-10-07T14:32:10.348830Z",
"id": "CVE-2025-59425",
"options": [
{
"exploitation": "none"
},
{
"automatable": "yes"
},
{
"technicalImpact": "partial"
}
],
"role": "CISA Coordinator",
"version": "2.0.3"
}
}
]
},
"weaknesses": [
{
"source": "[email protected]",
"type": "Secondary",
"description": [
{
"lang": "en",
"value": "CWE-385"
}
]
}
],
"configurations": [
{
"nodes": [
{
"operator": "OR",
"negate": false,
"cpeMatch": [
{
"vulnerable": true,
"criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
"versionEndExcluding": "0.11.0",
"matchCriteriaId": "99A24E23-769D-4DB8-BF37-EEC71EE83630"
},
{
"vulnerable": true,
"criteria": "cpe:2.3:a:vllm:vllm:0.11.0:rc1:*:*:*:*:*:*",
"matchCriteriaId": "46639D64-5C28-44F3-AE25-9212114AFC8E"
}
]
}
]
}
],
"references": [
{
"url": "https://github.com/vllm-project/vllm/blob/4b946d693e0af15740e9ca9c0e059d5f333b1083/vllm/entrypoints/openai/api_server.py#L1270-L1274",
"source": "[email protected]",
"tags": [
"Product"
]
},
{
"url": "https://github.com/vllm-project/vllm/commit/ee10d7e6ff5875386c7f136ce8b5f525c8fcef48",
"source": "[email protected]",
"tags": [
"Patch"
]
},
{
"url": "https://github.com/vllm-project/vllm/releases/tag/v0.11.0",
"source": "[email protected]",
"tags": [
"Release Notes"
]
},
{
"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-wr9h-g72x-mwhm",
"source": "[email protected]",
"tags": [
"Exploit",
"Vendor Advisory"
]
}
]
}